Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds non-obvious behavioral guidance: results are evidence not permission, a missing plan must not be used to invent faster replies or channels, and evaluate_support_promise must gate any claim. That is genuine added context beyond the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the primary action before the constraints. Each sentence carries a distinct point (what it returns, what it is not, what a miss means, what to call next), with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists, so return values need no explanation, and the anti-hallucination guidance is strong. The gap is on the input side: with 0% schema coverage, the description says nothing about catalogId, question format, or the limit parameter, leaving invocation details underspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, so the description must compensate and largely does not. 'Question' is only loosely implied by 'match a support question,' and catalogId and the limit/pagination behavior are entirely undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Retrieve') and resource ('customer plans that match a support question') and enumerates the related artifacts returned (reply windows, channels, staffing promises). It is clear on its own, but never distinguishes itself from the sibling search_customer_plans, which sounds like it does something similar.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete follow-up rule: 'Call evaluate_support_promise before stating any of them,' and frames the output as evidence rather than permission. It does not, however, say when to prefer this tool over search_customer_plans or the list_* siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.